From 43de30d36742dbbde22f2ad526c3e5a403c271e2 Mon Sep 17 00:00:00 2001 From: Sam Tebbs Date: Thu, 27 May 2021 16:34:41 +0100 Subject: [PATCH] arm64: Import latest version of Cortex Strings' memcmp Import the latest version of the former Cortex Strings - now Arm Optimized Routines - memcmp function based on the upstream code of string/aarch64/memcmp.S at commit e823e3a from https://github.com/ARM-software/optimized-routines Note that for simplicity Arm have chosen to contribute this code to Linux under GPLv2 rather than the original MIT license. Signed-off-by: Sam Tebbs [ rm: update attribution and commit message ] Signed-off-by: Robin Murphy Acked-by: Mark Rutland Link: https://lore.kernel.org/r/2889de2d41054f3f508fb3addad784a3606ef383.1622128527.git.robin.murphy@arm.com Signed-off-by: Will Deacon --- arch/arm64/lib/memcmp.S | 346 +++++++++++++++++------------------------------- 1 file changed, 119 insertions(+), 227 deletions(-) diff --git a/arch/arm64/lib/memcmp.S b/arch/arm64/lib/memcmp.S index c0671e7..498f0d9 100644 --- a/arch/arm64/lib/memcmp.S +++ b/arch/arm64/lib/memcmp.S @@ -1,247 +1,139 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (C) 2013 ARM Ltd. - * Copyright (C) 2013 Linaro. + * Copyright (c) 2013-2020, Arm Limited. * - * This code is based on glibc cortex strings work originally authored by Linaro - * be found @ - * - * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/ - * files/head:/src/aarch64/ + * Adapted from the original at: + * https://github.com/ARM-software/optimized-routines/blob/master/string/aarch64/memcmp.S */ #include #include -/* -* compare memory areas(when two memory areas' offset are different, -* alignment handled by the hardware) -* -* Parameters: -* x0 - const memory area 1 pointer -* x1 - const memory area 2 pointer -* x2 - the maximal compare byte length -* Returns: -* x0 - a compare result, maybe less than, equal to, or greater than ZERO -*/ +/* Assumptions: + * + * ARMv8-a, AArch64, unaligned accesses. + */ + +#define L(label) .L ## label /* Parameters and result. */ -src1 .req x0 -src2 .req x1 -limit .req x2 -result .req x0 +#define src1 x0 +#define src2 x1 +#define limit x2 +#define result w0 /* Internal variables. */ -data1 .req x3 -data1w .req w3 -data2 .req x4 -data2w .req w4 -has_nul .req x5 -diff .req x6 -endloop .req x7 -tmp1 .req x8 -tmp2 .req x9 -tmp3 .req x10 -pos .req x11 -limit_wd .req x12 -mask .req x13 +#define data1 x3 +#define data1w w3 +#define data1h x4 +#define data2 x5 +#define data2w w5 +#define data2h x6 +#define tmp1 x7 +#define tmp2 x8 SYM_FUNC_START_WEAK_PI(memcmp) - cbz limit, .Lret0 - eor tmp1, src1, src2 - tst tmp1, #7 - b.ne .Lmisaligned8 - ands tmp1, src1, #7 - b.ne .Lmutual_align - sub limit_wd, limit, #1 /* limit != 0, so no underflow. */ - lsr limit_wd, limit_wd, #3 /* Convert to Dwords. */ - /* - * The input source addresses are at alignment boundary. - * Directly compare eight bytes each time. - */ -.Lloop_aligned: - ldr data1, [src1], #8 - ldr data2, [src2], #8 -.Lstart_realigned: - subs limit_wd, limit_wd, #1 - eor diff, data1, data2 /* Non-zero if differences found. */ - csinv endloop, diff, xzr, cs /* Last Dword or differences. */ - cbz endloop, .Lloop_aligned - - /* Not reached the limit, must have found a diff. */ - tbz limit_wd, #63, .Lnot_limit - - /* Limit % 8 == 0 => the diff is in the last 8 bytes. */ - ands limit, limit, #7 - b.eq .Lnot_limit - /* - * The remained bytes less than 8. It is needed to extract valid data - * from last eight bytes of the intended memory range. - */ - lsl limit, limit, #3 /* bytes-> bits. */ - mov mask, #~0 -CPU_BE( lsr mask, mask, limit ) -CPU_LE( lsl mask, mask, limit ) - bic data1, data1, mask - bic data2, data2, mask - - orr diff, diff, mask - b .Lnot_limit - -.Lmutual_align: - /* - * Sources are mutually aligned, but are not currently at an - * alignment boundary. Round down the addresses and then mask off - * the bytes that precede the start point. - */ - bic src1, src1, #7 - bic src2, src2, #7 - ldr data1, [src1], #8 - ldr data2, [src2], #8 - /* - * We can not add limit with alignment offset(tmp1) here. Since the - * addition probably make the limit overflown. - */ - sub limit_wd, limit, #1/*limit != 0, so no underflow.*/ - and tmp3, limit_wd, #7 - lsr limit_wd, limit_wd, #3 - add tmp3, tmp3, tmp1 - add limit_wd, limit_wd, tmp3, lsr #3 - add limit, limit, tmp1/* Adjust the limit for the extra. */ - - lsl tmp1, tmp1, #3/* Bytes beyond alignment -> bits.*/ - neg tmp1, tmp1/* Bits to alignment -64. */ - mov tmp2, #~0 - /*mask off the non-intended bytes before the start address.*/ -CPU_BE( lsl tmp2, tmp2, tmp1 )/*Big-endian.Early bytes are at MSB*/ - /* Little-endian. Early bytes are at LSB. */ -CPU_LE( lsr tmp2, tmp2, tmp1 ) - - orr data1, data1, tmp2 - orr data2, data2, tmp2 - b .Lstart_realigned - - /*src1 and src2 have different alignment offset.*/ -.Lmisaligned8: - cmp limit, #8 - b.lo .Ltiny8proc /*limit < 8: compare byte by byte*/ - - and tmp1, src1, #7 - neg tmp1, tmp1 - add tmp1, tmp1, #8/*valid length in the first 8 bytes of src1*/ - and tmp2, src2, #7 - neg tmp2, tmp2 - add tmp2, tmp2, #8/*valid length in the first 8 bytes of src2*/ - subs tmp3, tmp1, tmp2 - csel pos, tmp1, tmp2, hi /*Choose the maximum.*/ - - sub limit, limit, pos - /*compare the proceeding bytes in the first 8 byte segment.*/ -.Ltinycmp: - ldrb data1w, [src1], #1 - ldrb data2w, [src2], #1 - subs pos, pos, #1 - ccmp data1w, data2w, #0, ne /* NZCV = 0b0000. */ - b.eq .Ltinycmp - cbnz pos, 1f /*diff occurred before the last byte.*/ - cmp data1w, data2w - b.eq .Lstart_align -1: - sub result, data1, data2 + subs limit, limit, 8 + b.lo L(less8) + + ldr data1, [src1], 8 + ldr data2, [src2], 8 + cmp data1, data2 + b.ne L(return) + + subs limit, limit, 8 + b.gt L(more16) + + ldr data1, [src1, limit] + ldr data2, [src2, limit] + b L(return) + +L(more16): + ldr data1, [src1], 8 + ldr data2, [src2], 8 + cmp data1, data2 + bne L(return) + + /* Jump directly to comparing the last 16 bytes for 32 byte (or less) + strings. */ + subs limit, limit, 16 + b.ls L(last_bytes) + + /* We overlap loads between 0-32 bytes at either side of SRC1 when we + try to align, so limit it only to strings larger than 128 bytes. */ + cmp limit, 96 + b.ls L(loop16) + + /* Align src1 and adjust src2 with bytes not yet done. */ + and tmp1, src1, 15 + add limit, limit, tmp1 + sub src1, src1, tmp1 + sub src2, src2, tmp1 + + /* Loop performing 16 bytes per iteration using aligned src1. + Limit is pre-decremented by 16 and must be larger than zero. + Exit if <= 16 bytes left to do or if the data is not equal. */ + .p2align 4 +L(loop16): + ldp data1, data1h, [src1], 16 + ldp data2, data2h, [src2], 16 + subs limit, limit, 16 + ccmp data1, data2, 0, hi + ccmp data1h, data2h, 0, eq + b.eq L(loop16) + + cmp data1, data2 + bne L(return) + mov data1, data1h + mov data2, data2h + cmp data1, data2 + bne L(return) + + /* Compare last 1-16 bytes using unaligned access. */ +L(last_bytes): + add src1, src1, limit + add src2, src2, limit + ldp data1, data1h, [src1] + ldp data2, data2h, [src2] + cmp data1, data2 + bne L(return) + mov data1, data1h + mov data2, data2h + cmp data1, data2 + + /* Compare data bytes and set return value to 0, -1 or 1. */ +L(return): +#ifndef __AARCH64EB__ + rev data1, data1 + rev data2, data2 +#endif + cmp data1, data2 +L(ret_eq): + cset result, ne + cneg result, result, lo ret -.Lstart_align: - lsr limit_wd, limit, #3 - cbz limit_wd, .Lremain8 - - ands xzr, src1, #7 - b.eq .Lrecal_offset - /*process more leading bytes to make src1 aligned...*/ - add src1, src1, tmp3 /*backwards src1 to alignment boundary*/ - add src2, src2, tmp3 - sub limit, limit, tmp3 - lsr limit_wd, limit, #3 - cbz limit_wd, .Lremain8 - /*load 8 bytes from aligned SRC1..*/ - ldr data1, [src1], #8 - ldr data2, [src2], #8 - - subs limit_wd, limit_wd, #1 - eor diff, data1, data2 /*Non-zero if differences found.*/ - csinv endloop, diff, xzr, ne - cbnz endloop, .Lunequal_proc - /*How far is the current SRC2 from the alignment boundary...*/ - and tmp3, tmp3, #7 - -.Lrecal_offset:/*src1 is aligned now..*/ - neg pos, tmp3 -.Lloopcmp_proc: - /* - * Divide the eight bytes into two parts. First,backwards the src2 - * to an alignment boundary,load eight bytes and compare from - * the SRC2 alignment boundary. If all 8 bytes are equal,then start - * the second part's comparison. Otherwise finish the comparison. - * This special handle can garantee all the accesses are in the - * thread/task space in avoid to overrange access. - */ - ldr data1, [src1,pos] - ldr data2, [src2,pos] - eor diff, data1, data2 /* Non-zero if differences found. */ - cbnz diff, .Lnot_limit - - /*The second part process*/ - ldr data1, [src1], #8 - ldr data2, [src2], #8 - eor diff, data1, data2 /* Non-zero if differences found. */ - subs limit_wd, limit_wd, #1 - csinv endloop, diff, xzr, ne/*if limit_wd is 0,will finish the cmp*/ - cbz endloop, .Lloopcmp_proc -.Lunequal_proc: - cbz diff, .Lremain8 - -/* There is difference occurred in the latest comparison. */ -.Lnot_limit: -/* -* For little endian,reverse the low significant equal bits into MSB,then -* following CLZ can find how many equal bits exist. -*/ -CPU_LE( rev diff, diff ) -CPU_LE( rev data1, data1 ) -CPU_LE( rev data2, data2 ) - - /* - * The MS-non-zero bit of DIFF marks either the first bit - * that is different, or the end of the significant data. - * Shifting left now will bring the critical information into the - * top bits. - */ - clz pos, diff - lsl data1, data1, pos - lsl data2, data2, pos - /* - * We need to zero-extend (char is unsigned) the value and then - * perform a signed subtraction. - */ - lsr data1, data1, #56 - sub result, data1, data2, lsr #56 + .p2align 4 + /* Compare up to 8 bytes. Limit is [-8..-1]. */ +L(less8): + adds limit, limit, 4 + b.lo L(less4) + ldr data1w, [src1], 4 + ldr data2w, [src2], 4 + cmp data1w, data2w + b.ne L(return) + sub limit, limit, 4 +L(less4): + adds limit, limit, 4 + beq L(ret_eq) +L(byte_loop): + ldrb data1w, [src1], 1 + ldrb data2w, [src2], 1 + subs limit, limit, 1 + ccmp data1w, data2w, 0, ne /* NZCV = 0b0000. */ + b.eq L(byte_loop) + sub result, data1w, data2w ret -.Lremain8: - /* Limit % 8 == 0 =>. all data are equal.*/ - ands limit, limit, #7 - b.eq .Lret0 - -.Ltiny8proc: - ldrb data1w, [src1], #1 - ldrb data2w, [src2], #1 - subs limit, limit, #1 - - ccmp data1w, data2w, #0, ne /* NZCV = 0b0000. */ - b.eq .Ltiny8proc - sub result, data1, data2 - ret -.Lret0: - mov result, #0 - ret SYM_FUNC_END_PI(memcmp) EXPORT_SYMBOL_NOKASAN(memcmp) -- 2.7.4